Claude Sonnet 5.5 · DRACO · 100-task Perplexity deep-research benchmark · 成绩与配置

Claude Sonnet 5.5 的 DRACO · 100-task Perplexity deep-research benchmark 记录。本次发布有 5 条成绩记录,含 5 条精确值(可含历史记录),附 2 条来源定位。

成绩与评测条件

Claude Sonnet 5.5 · DRACO 成绩与配置
指标与成绩配置与评测条件出处
Normalized score64.6%原文 64.6% · 单位 %
公布 未确认
Low effort
设置
Low reasoning effort.
未知项
Sampling settings not stated unless recorded per result.
工具
允许工具
推理预算
low
框架
未记录
协议
DRACO, 100 curated tasks; normalized score from five independent rubric-grading runs per response.
条件
Figure labels the effort Low; web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget; Claude Opus 4.6 grader. The report says its modified tools, prompts, and grader make results not directly comparable to Perplexity's version.
在排名中查看此成绩
Normalized score71.2%原文 71.2% · 单位 %
公布 未确认
Medium effort
设置
Medium reasoning effort.
未知项
Sampling settings not stated unless recorded per result.
工具
允许工具
推理预算
med
框架
未记录
协议
DRACO, 100 curated tasks; normalized score from five independent rubric-grading runs per response.
条件
Figure labels the effort Med; web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget; Claude Opus 4.6 grader. The report says its modified tools, prompts, and grader make results not directly comparable to Perplexity's version.
在排名中查看此成绩
Normalized score81%原文 81.0% · 单位 %
公布 未确认
High effort
设置
High reasoning effort.
未知项
Sampling settings not stated unless recorded per result.
工具
允许工具
推理预算
high
框架
未记录
协议
DRACO, 100 curated tasks; normalized score from five independent rubric-grading runs per response.
条件
Figure labels the effort High; web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget; Claude Opus 4.6 grader. The report says its modified tools, prompts, and grader make results not directly comparable to Perplexity's version.
在排名中查看此成绩
Normalized score85.7%原文 85.7% · 单位 %
公布 未确认
Xhigh effort
设置
Xhigh reasoning effort.
未知项
Sampling settings not stated unless recorded per result.
工具
允许工具
推理预算
xhigh
框架
未记录
协议
DRACO, 100 curated tasks; normalized score from five independent rubric-grading runs per response.
条件
Figure labels the effort Xhigh; web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget; Claude Opus 4.6 grader. The report says its modified tools, prompts, and grader make results not directly comparable to Perplexity's version.
在排名中查看此成绩
Normalized score87%原文 87.0% · 单位 %
公布 未确认
Max effort
设置
Max reasoning effort.
未知项
Adaptive thinking status is benchmark-specific.
工具
允许工具
推理预算
max
框架
未记录
协议
DRACO, 100 curated tasks; normalized score from five independent rubric-grading runs per response.
条件
Figure labels the effort Max; web search, web fetch, programmatic tool calling, and code execution; 980k-token task budget; Claude Opus 4.6 grader. The report says its modified tools, prompts, and grader make results not directly comparable to Perplexity's version.
在排名中查看此成绩

出处与披露

测试版本与指标

别名 Deep Research Accuracy, Completeness, and Objectivity

  • Normalized score · % · 越高越好